WO2021018232A1

WO2021018232A1 - Adaptive evaluation method and apparatus, storage medium, and electronic device

Info

Publication number: WO2021018232A1
Application number: PCT/CN2020/105743
Authority: WO
Inventors: 乔丹•奈尔森施特格尔; 尹天骄; 许晓秋; 杜舒
Original assignee: 北京大米科技有限公司
Priority date: 2019-07-29
Filing date: 2020-07-30
Publication date: 2021-02-04
Also published as: CN110489454A

Abstract

An adaptive evaluation method and apparatus, a storage medium, and an electronic device. Said method comprises: pushing, on the basis of a teaching level corresponding to a student, to a student at least one test question of first difficulty level in a question library, and acquiring first answer information of the student for the at least one test question of first difficulty level (S101); extracting first feature information of the first answer information, and calculating a first correct rate of the first answer information on the basis of the first feature information (S102); pushing, on the basis of the first correct rate, to the student at least one test question of target difficulty (S103); acquiring second answer information of the student for the at least one test question of target difficulty (S104); extracting second feature information of the second answer information, and calculating a second correct rate of the second answer information on the basis of the second feature information (S105); and determining an evaluation result of the student on the basis of the second correct rate (S106). Said method can push a suitable test question according to the actual situation of a student, and can accurately perform personalized tests for various students.

Description

Adaptive evaluation method, device, storage medium and electronic equipment

Technical field

This application relates to the field of computer technology, in particular to an adaptive evaluation method, device, storage medium and electronic equipment.

Background technique

With the development of society, more and more people will choose to learn a variety of knowledge to continuously expand themselves. Among them, the traditional face-to-face teaching between students and teachers requires both parties to spend a lot of time and energy on the road. Therefore, with the development of the communication era, online teaching has been accepted by the majority of users.

The so-called online teaching means that students and teachers can use their own terminals to realize remote video teaching through the Internet. Of course, in order to meet individualized teaching needs, individualized customization can be made by evaluating students' test scores. The current assessment method is to select fixed questions in the question bank and push them to students, and conduct assessments based on the correct rate of students' answers. Because this evaluation method uses fixed questions, it is impossible to push more suitable test questions based on the actual situation of the students, which leads to the inability to accurately conduct personalized tests for each student.

Summary of the invention

The embodiments of the present application provide an adaptive evaluation method, device, storage medium, and electronic equipment, which can push appropriate test questions according to the actual situation of students, and can accurately perform personalized tests for each student. The technical solution is as follows:

In the first aspect, an embodiment of the present application provides an adaptive evaluation method, the method includes:

Push at least one first difficulty test question in the question bank to the student based on the teaching level corresponding to the student, and obtain the student's first answer information for the at least one first difficulty test question;

Extracting first characteristic information of the first answer information, and calculating a first correct rate of the first answer information based on the first characteristic information;

Push at least one target difficulty test question to the student based on the first correctness rate;

Acquiring second answer information of the student for the at least one target difficulty test question;

Extracting second characteristic information of the second answer information, and calculating a second correctness rate of the second answer information based on the second characteristic information;

Based on the second correctness rate, the evaluation result of the student is determined.

In the second aspect, an embodiment of the present application provides an adaptive evaluation device, the device including:

The first answer obtaining module is configured to push at least one first difficulty test question in the question bank to the student based on the student's corresponding teaching level, and obtain the student's first answer information for the at least one first difficulty test question;

The first correct rate calculation module is configured to extract the first characteristic information of the first answer information, and calculate the first correct rate of the first answer information based on the first characteristic information;

A target test question push module, configured to push at least one target difficulty test question to the student based on the first correctness rate;

The second answer obtaining module is used to obtain the second answer information of the student for the at least one target difficulty test question;

A second correct rate calculation module, configured to extract second feature information of the second answer information, and calculate a second correct rate of the second answer information based on the second feature information;

The evaluation result determination module is configured to determine the evaluation result of the student based on the second correctness rate.

In a third aspect, an embodiment of the present application provides a computer storage medium storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above method steps .

The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

In one or more embodiments of the present application, at least one first difficulty test question in the question bank is pushed to the student based on the student's teaching level, and at least one first difficulty test question is pushed to the student according to the first correct rate of the first difficulty test question For the target difficulty test question, the evaluation result is determined by the second answer information of the target difficulty test question. By pushing the test questions of adaptable difficulty based on the student's teaching level, and dynamically selecting the follow-up difficulty (one higher or the same or lower) test questions according to the correct answer rate, and pushing the appropriate test questions according to the actual situation of the students, it can be accurate Each student conducts personalized tests to meet individual teaching needs.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of an adaptive evaluation method provided by an embodiment of the present application;

FIG. 2 is a schematic flowchart of a performance evaluation method provided by an embodiment of the present application;

3 is a schematic diagram of an example of a question bank provided by an embodiment of the present application;

4 is a schematic diagram of an example of an exam question push page provided by an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a performance evaluation device provided by an embodiment of the present application;

Fig. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. Rather, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.

In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above-mentioned terms in this application can be understood under specific circumstances. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And/or" describes the association relationship of the associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are in an "or" relationship.

The application will be described below in conjunction with specific embodiments.

Hereinafter, the adaptive evaluation method provided by the embodiment of the present application will be introduced in detail with reference to FIG. 1 to FIG. 4. Wherein, the adaptive evaluation device in the embodiment of the present application may be a user terminal, and the user terminal includes, but is not limited to: a personal computer, a tablet computer, a handheld device, a vehicle-mounted device, a wearable device, a computing device, or a device connected to a wireless modem Other processing equipment, etc. In different networks, user terminals can be called different names, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication Device, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), terminal equipment in 5G network or future evolution network, etc.

Please refer to FIG. 1, which is a schematic flowchart of an adaptive evaluation method provided by an embodiment of this application. As shown in FIG. 1, the adaptive evaluation method of the embodiment of the present application may include the following steps:

S101: Push at least one first difficulty test question in the question bank to the student based on the teaching level corresponding to the student, and obtain first answer information of the student for the at least one first difficulty test question;

The question bank includes test questions of different difficulty levels, and each difficulty level can include multiple test questions. And, each difficulty level corresponds to the student's teaching level one to one.

As shown in Table 1, the question bank includes 5 difficulty levels: A, B, C, D, and E, and the corresponding test questions are S1, S2, S3, S4, and S5. And S1, S2, S3, S4, S5 respectively include multiple test questions. At the same time, students’ teaching levels include 5

levels

1, 2, 3, 4, and 5, which correspond to A, B, C, D, and E in the question bank respectively.

Table 1

The teaching level can be determined based on factors such as the age of the student and the length of class. Different age ranges and different length of class correspond to different teaching levels.

For example, as shown in Table 2, the user’s teaching level can be uniquely determined by the user’s age range and class duration. Among them, 1-5, the larger the value, the higher the teaching level. If a student’s age is 25 and the length of class is 20 months, the corresponding teaching level is level 3.

Table 2

In the specific implementation, the student’s teaching level is determined according to factors such as the student’s age and class duration, and then the difficulty level of the test question corresponding to the teaching level is searched. After the difficulty level is determined, the question corresponding to the difficulty level is randomly followed A preset number of test questions (first difficulty test questions) are pushed to the student, and the student answers these first difficulty test questions. After the answers are completed, the corresponding answer information (first answer information) is obtained.

For example, if the teaching level of a certain student X is level 3, the corresponding difficulty level is C. Therefore, select at least one (such as 3) test questions in S3 and push it to X, and obtain X's answer information for these 3 test questions.

S102: Extract first feature information of the first answer information, and calculate a first correct rate of the first answer information based on the first feature information;

The first feature information is related to the content of the first answer information. For example, the first answer information may be voice information, text information, or picture information.

Taking the test question as an oral test as an example, and the first answer information is voice information, the first feature information may include rhythm features, accent features, prosodic features, clarity, and so on.

Among them, the rhythm feature refers to the pause position and pause duration between words or syllables and syllables when the user pronounces.

Stress refers to the accentuation of pronunciation due to scene changes, which refers to which word should be emphasized in a whole sentence, or which syllable should be emphasized in a word.

Prosodic features refer to the expression of circumflex and frustration of pronunciation, which can include the rhythm of each word, the rhythm of each sentence, the rhythm of each paragraph, and so on.

Clarity means that the pronunciation of each character or word should be round and round, and there is no unclear or unclear ending sound.

For another example, taking the test question as a silent poem, and the first answer information is text information, the first feature information may include letter composition, word order, etc.

Among them, the constituent letters refer to which letters a word is composed of, and the order of these letters.

The word order is the sequence of words that express a sentence (a meaning).

In a specific implementation, the first feature information of the first answer information is extracted, and the first feature information is compared with the feature information of the correct answer information one by one, so as to obtain the first correct rate of the student for the first difficulty test question.

In another specific implementation, the first feature information of the first answer information is extracted, and the first feature information and the feature information of the correct answer information are subjected to vector operations, such as cosine similarity, distance similarity calculation, etc., to obtain the student The first correct rate for the first difficulty test.

S103: Push at least one target difficulty test question to the student based on the first correctness rate;

The order of high and low can be understood as that the difficulty level of the first grade difficulty test is greater than the difficulty level of the target difficulty test. If the difficulty level of the test question corresponding to the target difficulty test is C, the difficulty level of the first grade difficulty test is D or E.

When the first correct rate is less than the first threshold, it indicates that these test questions have a certain degree of difficulty for the student, and at least one test question with a lower difficulty level in the question bank is taken as the Target difficulty test questions and push them to the students.

When the first correct rate is greater than or equal to the first threshold and less than the second threshold, it indicates that these questions are of moderate difficulty for the student. In order to further determine that it is due to luck or misunderstanding or personal ability, the At least one other test question of the same difficulty level as the first difficulty test question in the question bank is used as the target difficulty test question, and is pushed to the student. Wherein, the first threshold is less than the second threshold.

When the first correct rate is greater than or equal to the second threshold, it indicates that these several test questions are relatively easy for the student, and the higher difficulty level in the question bank is selected according to the order of the difficulty level of the test questions in the question bank. At least one test question is used as the target difficulty test question and pushed to the student.

Among them, the high-difficulty test questions or the low-difficulty test questions can include at least one. The number of high-difficulty test questions or low-difficulty test questions can be determined according to the correct rate of the students for the first-difficulty test questions, or a fixed number of higher one Test questions or lower one difficulty test questions.

For example, if the first correct rate threshold is 80%, when the student's correct rate for the target difficulty test question is between 80%-85%, the number of next difficulty test questions is 3, when the student is correct for the target difficulty test question When the rate is between 85% and 90%, the number of next difficulty test questions is 4, and when the student’s correct rate for the target difficulty test is between 90% and 100%, the number of next difficulty test questions is 5 One.

table 3

正确率Correct rate	推送个数Push number
80％-85％80%-85%	33
85％-90％85%-90%	44
90％-100％90%-100%	55

For another example, as long as the student's correct rate for the target difficulty test question is greater than or equal to the preset correct rate threshold, then three next difficulty test questions are pushed.

S104: Acquire second answer information of the student for the at least one target difficulty test question.

The second answer information written by the user for the target difficulty can be collected through a voice collection device or a touch screen device.

It should be noted that the second answer information and the first answer information may be the same type of answer information. For example, the first answer information is a voice answer, and the second answer information is also a voice answer, which is a test for the same type of exam.

S105. Extract second characteristic information of the second answer information, and calculate a second correctness rate of the second answer information based on the second characteristic information;

The calculation method of the second correctness rate may be the same as the calculation method of the first correctness rate. For details, refer to S102, which will not be repeated here.

In addition, the first correctness rate and/or the second correctness rate can also be calculated based on the trained neural network model. Specifically, the neural network model can perform feature extraction and calculation to obtain the final calculation result.

S106: Determine an evaluation result of the student based on the second correctness rate.

The second correct rate threshold may be 70%, 75%, 80%, 85%, 90%, etc.

Optionally, the statistics of student evaluation results can be calculated based on pre-trained neural network models, such as Convolutional Neural Networks (CNN, or Deep Convolutional Neural Networks, DCNN), Deconvolutional Networks , DN), also known as inverse graphics networks (IGN), recurrent neural networks (RNN), long/short term memory (LSTM), etc. That is, the second accuracy rate, difficulty level, teaching level and other information are used as the input of the model, and the corresponding evaluation result can be obtained. The evaluation result can be the number of test scores, the test rating, etc.

Please refer to FIG. 2, which is a schematic flowchart of an adaptive evaluation method provided by an embodiment of this application. In this embodiment, the adaptive evaluation method is applied to the user terminal as an example. The adaptive evaluation method may include the following steps:

S201: Acquire the teaching level of the student, and determine the difficulty level of the test question corresponding to the teaching level based on the corresponding relationship between the teaching level and the difficulty level of the test questions in the question bank;

The teaching level can be determined based on factors such as the age of the student and the length of class. Different age ranges and different class duration correspond to different class levels. The teaching level can be divided into 1, 2, 3, 4, 5, etc. The higher the value, the higher the corresponding level.

If you currently need to evaluate the performance of a student, you can search for the student’s current teaching level based on the student’s age and class duration.

The question bank includes test questions of different difficulty levels, and each difficulty level can include multiple test questions. Moreover, each difficulty level corresponds to the student's teaching level one-to-one. After the student's teaching level is determined, the corresponding first difficulty level can be determined.

S202: Obtain at least one first difficulty test question corresponding to the test question difficulty level in the question bank, and push the at least one first difficulty test question to the student;

For example, as shown in Figure 3 is a schematic diagram of the question bank, which includes multiple sub-question banks such as S1, S2, S3, S4, and S5. The corresponding difficulty levels of each sub-question bank are A, B, C, D, E, and A< B<C<D<E.

There are multiple test questions in each sub-question bank. If the determined difficulty level of the test question is C, at least one test question is randomly obtained in S3 and pushed to the student.

Among them, the method of obtaining test questions in the sub-question bank may be to randomly select a fixed number of test questions, or to randomly select a predetermined percentage based on the number of test questions in the sub-question bank.

For example, if there are 100 questions in S1 and the preset percentage is 5%, then 5 questions in S1 are randomly selected and pushed.

Wherein, the push method may be that the system randomly selects test questions according to preset rules, and then displays them on the display interface of the user terminal. The display method can be to display multiple questions on the same page, or to display only one question on the current display page, and jump to display the next question after the user has finished answering the question.

For example, as shown in FIG. 4, a schematic diagram of a test question push display effect is displayed, in which the current difficulty level test question number "current test question includes 5 questions", the content of the test question, and a button control to jump to the next question are displayed.

S203: Acquire first answer information of the student for the at least one first difficulty test question;

After the student finishes answering the above-mentioned pushed test questions and confirms (for example, clicking the "confirm" button on the display interface), the user terminal reads the student's first answer information.

For example, the student's answer information for the 5 questions obtained by the user terminal is A, A, B, B, and C respectively.

Optionally, if the examination question requires a student to perform a voice assessment (for example, reading each word or sentence to determine whether the pronunciation is accurate), the pronunciation information of the student is adopted by the voice collection device, and the pronunciation information is used as the first answer information.

S204. Extract the first feature information of the first answer information, and calculate the first correctness rate based on the correlation between the first feature information and first reference feature information, where the first reference information is the first 1. The characteristic information of the reference answer of the difficulty test;

In specific implementation, the correlation refers to similarity or distance. A feasible implementation is to extract the first feature information of the first answer information, and compare the first feature information with the first reference feature information of the correct answer information one by one to obtain the similarity between the two, and compare the Similarity is used as the first correct rate to describe the first difficulty test questions. The higher the similarity, the higher the first correct rate. Another feasible implementation method is to calculate the correlation between the two to calculate the distance between the two, and obtain the first correct rate according to the distance, for example, the reciprocal of the calculated distance is used as the first correct rate, The greater the calculated distance, the lower the first correct rate, or the first correct rate is calculated by performing the cosine similarity of the feature vector, and so on.

Among them, the first answer information needs to be aligned with the first reference feature information and then compared one by one. The rhythm can be expressed by the pause duration. If the pause is 0.4 seconds, the rhythm of the word is 0.4. If 1 represents accent and 0 represents non-stress, the accent feature of the corresponding voice segment of the sentence in the user's speech can be expressed as a vector (1,0,0,0). Prosody and clarity can also be expressed by vector coding. Then express each feature information in the form of row vector or column vector for each word in a predetermined order, so as to obtain the matrix corresponding to each sentence, and then align and compare each corresponding matrix.

It should be noted that the correlation between the two can be calculated sentence by sentence, and then the first correct rate is obtained sentence by sentence, and finally the final first correct rate is obtained according to the weight.

S205: When the first correctness rate is less than the first threshold, at least one test question with a lower difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed to Said student

The first correct rate threshold is a correct rate preset for the target difficulty level, and may be a reasonable value obtained by empirical statistics. It is also possible to set the same correct rate for test questions of various difficulty levels, that is, for test questions of different difficulty levels such as A, B, C, D, and E, the correct rate thresholds are all the same.

For example, if the student's teaching level is 3 and the difficulty level of the first difficulty test is C, then the B-level test questions should be searched and pushed to the student, that is, the test questions in the S2 question bank should be searched and pushed. Optionally, if the difficulty level of the student's first difficulty test is A, then the push ends at this time.

S206: When the first correct rate is greater than or equal to the first threshold and less than the second threshold, use at least one other test question in the question bank with the same difficulty level as the first difficulty test question as the target difficulty test question , And push to the student;

For example, if the student's teaching level is 3, and the difficulty level of the first difficulty test is C, then the C-level test questions should be searched for and pushed to the student, that is, continue to search for test questions in the S3 question bank for push.

S207: When the first correctness rate is greater than or equal to the second threshold, at least one test question with a higher difficulty level in the question bank is used as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, And push to the student;

For example, if the student's teaching level is 3 and the difficulty level of the first difficulty test is C, then the D-level test questions should be searched and pushed to the student, that is, the test questions in the S4 question bank should be searched and pushed.

S208: Acquire second answer information of the student for the at least one target difficulty test question;

The method for obtaining the second answer information can be the same as the method for obtaining the first answer information. For details, see S203, which is not repeated here.

S209. Extract second feature information of the second answer information, and calculate the second correctness rate based on the correlation between the second feature information and second reference feature information, where the second reference information is a target The characteristic information of the reference answer of the difficulty test;

The calculation method of the second correctness rate may be the same as the calculation method of the first correctness rate. For details, refer to S204, which will not be repeated here.

S210: Determine an evaluation result of the student based on the second correctness rate.

A feasible evaluation method is to obtain the answer correct rate corresponding to the answer information, determine the pronunciation level corresponding to the answer correct rate, and use the pronunciation level as the test result of the student.

For example, the correct rate of the student for grade C is 85% (greater than the first correct rate threshold), and the correct rate for grade D is 70% (less than the second correct rate threshold), using a preset algorithm to calculate the total correct rate (if 80%), and then according to the corresponding relationship between the correct rate and the test score (as shown in Table 4), the final test score of the student can be determined.

Table 4

正确率Correct rate	考试成绩Test score
大于或者等于95％Greater than or equal to 95%	A+A+
大于或者等于90，且小于95％Greater than or equal to 90 and less than 95%	AA
大于或者等于85％，且小于90％Greater than or equal to 85% and less than 90%	A-A-
大于或者等于80％，且小于85％Greater than or equal to 80% and less than 85%	B+B+
大于或者等于70％，且小于80％Greater than or equal to 70% and less than 80%	BB
小于70％Less than 70%	B-B-

Another evaluation method may be to use the second correctness rate as the input of the pre-trained evaluation model to obtain the evaluation result. For details, see S106, which will not be repeated here.

Optionally, when the second correctness rate is greater than or equal to the third correctness rate threshold, it indicates that the student can easily answer the test questions of the target difficulty level, and then the student can continue to push higher difficulty levels in the above manner The test questions are pushed directly to the test questions of the highest difficulty level in the question bank or when the correct rate of the answer information of a certain difficulty test question is less than the preset correct rate threshold, the push is ended.

The following are device embodiments of this application, which can be used to implement the method embodiments of this application. For details not disclosed in the device embodiment of this application, please refer to the method embodiment of this application.

Please refer to FIG. 5, which shows a schematic structural diagram of an adaptive evaluation device provided by an exemplary embodiment of the present application. The adaptive evaluation device can be implemented as all or a part of the user terminal through software, hardware or a combination of the two. The device 1 includes a first answer obtaining module 10, a first correct rate calculation module 20, a target test question pushing module 30, a second answer obtaining module 40, a second correct rate calculation module 50, and a test result determination module 60.

The first answer obtaining module 10 is configured to push at least one first difficulty test question in the question bank to the student based on the student's corresponding teaching level, and obtain the student's first answer information for the at least one first difficulty test question;

The first correct rate calculation module 20 is configured to extract first feature information of the first answer information, and calculate the first correct rate of the first answer information based on the first feature information;

The target test question pushing module 30 is configured to push at least one target difficulty test question to the student based on the first correctness rate;

The second answer obtaining module 40 is configured to obtain second answer information of the student for the at least one target difficulty test question;

The second correctness rate calculation module 50 is configured to extract second characteristic information of the second answer information, and calculate a second correctness rate of the second answer information based on the second characteristic information;

The evaluation result determination module 60 is configured to determine the evaluation result of the student based on the second correctness rate.

Optionally, the target test question pushing module 30 is specifically used for:

When the first correct rate is less than the first threshold, at least one test question with a lower difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed to the student;

And/or when the first correct rate is greater than or equal to the first threshold and less than the second threshold, use at least one other test question in the question bank with the same difficulty level as the first difficulty test question as the target difficulty Test questions and push them to said students; and/or

When the first correct rate is greater than or equal to the second threshold, at least one test question with a higher difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed To the student.

Optionally, the first correct rate and/or the second correct rate are calculated based on the trained neural network model.

Optionally, the first correct rate calculation module 20 is specifically configured to:

Calculate the first correct rate based on the correlation between the first feature information and the first reference feature information, where the first reference information is feature information of the reference answer of the first difficulty test question; and/or

The second correctness rate calculation module 50 is specifically configured to: calculate the second correctness rate based on the correlation between the second feature information and second reference feature information, where the second reference information is the target difficulty The characteristic information of the reference answer of the test question.

Optionally, the first answer obtaining module 10 is specifically used for:

Acquiring the teaching level of the student, and determining the difficulty level of the test question corresponding to the teaching level based on the corresponding relationship between the teaching level and the difficulty level of the test questions in the question bank;

Acquire at least one first difficulty test question corresponding to the test question difficulty level from the question bank, and push the at least one first difficulty test question to the student.

Optionally, the evaluation result includes student pronunciation level information.

It should be noted that when the adaptive evaluation device provided in the above embodiment executes the adaptive evaluation method, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functions can be allocated to different functions according to needs. Module completion means dividing the internal structure of the device into different functional modules to complete all or part of the functions described above. In addition, the self-adaptive evaluation device provided in the above-mentioned embodiment and the self-adaptive evaluation method embodiment belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

The serial numbers of the foregoing embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

The embodiments of the present application also provide a computer storage medium. The computer storage medium may store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps of the embodiments shown in FIGS. 1 to 4 above. For the specific execution process, refer to the specific description of the embodiment shown in FIG. 1 to FIG. 4, which is not repeated here.

Please refer to FIG. 6, which provides a schematic structural diagram of an electronic device according to an embodiment of this application. As shown in FIG. 6, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

Among them, the communication bus 1002 is used to implement connection and communication between these components.

The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

Among them, the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

The processor 1001 may include one or more processing cores. The processor 1001 uses various excuses and lines to connect various parts of the entire electronic device 1000, and executes by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Various functions and processing data of the electronic device 1000. Optionally, the processor 1001 may adopt at least one of digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA). A kind of hardware form to realize. The processor 1001 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is used to render and draw the content that the display needs to display; the modem is used to process wireless communication. It is understandable that the above-mentioned modem may not be integrated into the processor 1001, but may be implemented by a chip alone.

The memory 1005 may include random access memory (RAM) or read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a storage program area and a storage data area, where the storage program area may store instructions for implementing the operating system and instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), Instructions used to implement the foregoing method embodiments, etc.; the storage data area can store the data involved in the foregoing method embodiments. Optionally, the memory 1005 may also be at least one storage device located far away from the foregoing processor 1001. As shown in Fig. 6, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an adaptive evaluation application program.

In the electronic device 1000 shown in FIG. 6, the user interface 1003 is mainly used to provide an input interface for the user to obtain data input by the user; and the processor 1001 may be used to call an adaptive evaluation application program stored in the memory 1005, and Specifically perform the following operations:

In one embodiment, when the processor 1001 pushes at least one target difficulty test question to the student based on the first correctness rate, the processor 1001 specifically performs the following operations:

In an embodiment, the processor 1001 further performs the following operations:

The first correct rate and/or the second correct rate are calculated based on the trained neural network model.

In an embodiment, the processor 1001 specifically performs the following operations when performing the calculation of the first correctness rate:

The processor 1001 specifically performs the following operations when performing calculation of the second correctness rate:

The second correctness rate is calculated based on the correlation between the second feature information and the second reference feature information, where the second reference information is feature information of a reference answer of a target difficulty test question.

In one embodiment, when the processor 1001 pushes at least one first difficulty test question in the question bank to the student based on the teaching level corresponding to the student, the processor 1001 specifically performs the following operations:

In an embodiment, the evaluation result includes the pronunciation level information of the student.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through a computer program. The program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments. Wherein, the storage medium can be a magnetic disk, an optical disc, a read-only storage memory or a random storage memory, etc.

The above-disclosed are only the preferred embodiments of the application, which of course cannot be used to limit the scope of rights of the application. Therefore, equivalent changes made according to the claims of the application still fall within the scope of the application.

Claims

An adaptive evaluation method, characterized in that the method includes:

Push at least one first difficulty test question in the question bank to the student based on the teaching level corresponding to the student, and obtain the student's first answer information for the at least one first difficulty test question;

Extracting first characteristic information of the first answer information, and calculating a first correct rate of the first answer information based on the first characteristic information;

Push at least one target difficulty test question to the student based on the first correctness rate;

Acquiring second answer information of the student for the at least one target difficulty test question;

Extracting second characteristic information of the second answer information, and calculating a second correctness rate of the second answer information based on the second characteristic information;

Based on the second correctness rate, the evaluation result of the student is determined.
The method according to claim 1, wherein pushing at least one target difficulty test question to the student based on the first correctness rate comprises:

When the first correct rate is less than the first threshold, at least one test question with a lower difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed to the student;

And/or when the first correct rate is greater than or equal to the first threshold and less than the second threshold, use at least one other test question in the question bank with the same difficulty level as the first difficulty test question as the target difficulty Test questions and push them to said students; and/or

When the first correct rate is greater than or equal to the second threshold, at least one test question with a higher difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed To the student.
The method according to claim 1, wherein the first correctness rate and/or the second correctness rate are calculated based on a trained neural network model.
The method according to claim 3, wherein said calculating said first correct rate comprises:

Calculate the first correct rate based on the correlation between the first feature information and the first reference feature information, where the first reference information is feature information of the reference answer of the first difficulty test question; and/or

The calculating the second correctness rate includes: calculating the second correctness rate based on the correlation between the second characteristic information and the second reference characteristic information, wherein the second reference information is the value of the target difficulty test question Refer to the characteristic information of the answer.
The method according to claim 1, wherein the pushing at least one first difficulty test question in the question bank to the student based on the teaching level corresponding to the student comprises:

Acquiring the teaching level of the student, and determining the difficulty level of the test question corresponding to the teaching level based on the corresponding relationship between the teaching level and the difficulty level of the test questions in the question bank;

Acquire at least one first difficulty test question corresponding to the test question difficulty level from the question bank, and push the at least one first difficulty test question to the student.
The method according to claim 1, wherein the evaluation result includes student pronunciation level information.
An adaptive evaluation device, characterized in that the device includes:

The first answer obtaining module is configured to push at least one first difficulty test question in the question bank to the student based on the student's corresponding teaching level, and obtain the student's first answer information for the at least one first difficulty test question;

The first correct rate calculation module is configured to extract the first characteristic information of the first answer information, and calculate the first correct rate of the first answer information based on the first characteristic information;

A target test question push module, configured to push at least one target difficulty test question to the student based on the first correctness rate;

The second answer obtaining module is used to obtain the second answer information of the student for the at least one target difficulty test question;

A second correct rate calculation module, configured to extract second feature information of the second answer information, and calculate a second correct rate of the second answer information based on the second feature information;

The evaluation result determination module is configured to determine the evaluation result of the student based on the second correctness rate.
The device according to claim 7, wherein the target test question pushing module is specifically used for:

When the first correct rate is less than the first threshold, at least one test question with a lower difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed to the student;

And/or when the first correct rate is greater than or equal to the first threshold and less than the second threshold, use at least one other test question in the question bank with the same difficulty level as the first difficulty test question as the target difficulty Test questions and push them to said students; and/or

When the first correct rate is greater than or equal to the second threshold, at least one test question with a higher difficulty level in the question bank is taken as the target difficulty test question according to the order of the difficulty level of the test questions in the question bank, and is pushed To the student.
A computer storage medium, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 6.
An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and executed as claimed in any one of claims 1 to 6 Method steps.